© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11886
    Prev
    Next
    INDEX
    Explanations

    error codes and networking related acronyms, possibly focusing on "available"

    oai_token-act-pair · gemini-2.0-flash

    system errors

    np_max-act · gemini-2.0-flash

    A

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AC
    -1.07
     А
    -1.03
     AB
    -1.02
     AG
    -1.02
     AJ
    -1.02
     AD
    -1.02
     AK
    -0.96
     AW
    -0.93
     AN
    -0.89
     AH
    -0.88
    POSITIVE LOGITS
    are
    0.59
    aren
    0.59
    a
    0.57
    as
    0.56
    appro
    0.55
    évaluateur
    0.54
    Demografia
    0.53
    argout
    0.52
    aI
    0.51
    aba
    0.50
    Activations Density 1.534%

    No Known Activations